Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Graph Sampling-based Meta-Learning for Molecular Property Prediction (2306.16780v1)

Published 29 Jun 2023 in cs.LG and q-bio.BM

Abstract: Molecular property is usually observed with a limited number of samples, and researchers have considered property prediction as a few-shot problem. One important fact that has been ignored by prior works is that each molecule can be recorded with several different properties simultaneously. To effectively utilize many-to-many correlations of molecules and properties, we propose a Graph Sampling-based Meta-learning (GS-Meta) framework for few-shot molecular property prediction. First, we construct a Molecule-Property relation Graph (MPG): molecule and properties are nodes, while property labels decide edges. Then, to utilize the topological information of MPG, we reformulate an episode in meta-learning as a subgraph of the MPG, containing a target property node, molecule nodes, and auxiliary property nodes. Third, as episodes in the form of subgraphs are no longer independent of each other, we propose to schedule the subgraph sampling process with a contrastive loss function, which considers the consistency and discrimination of subgraphs. Extensive experiments on 5 commonly-used benchmarks show GS-Meta consistently outperforms state-of-the-art methods by 5.71%-6.93% in ROC-AUC and verify the effectiveness of each proposed module. Our code is available at https://github.com/HICAI-ZJU/GS-Meta.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (35)
  1. Low data drug discovery with one-shot learning. ACS central science, pages 283–293, 2017.
  2. Learning feed-forward one-shot learners. In NIPS, pages 523–531, 2016.
  3. Relational multi-task learning: Modeling relations between data and tasks. In ICLR, 2021.
  4. A closer look at few-shot classification. In ICLR, 2019.
  5. Molecular contrastive learning with chemical element knowledge graph. In AAAI, pages 3968–3976, 2022.
  6. Knowledge graph-enhanced molecular contrastive learning with functional prompt. Nature Machine Intelligence, pages 1–12, 2023.
  7. MELR: meta-learning via modeling episode-level relationships for few-shot learning. In ICLR, 2021.
  8. Fast graph representation learning with pytorch geometric. CoRR, 2019.
  9. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML, pages 1126–1135, 2017.
  10. High blood pressure and cardiovascular disease. Hypertension, pages 285–292, 2020.
  11. Few-shot graph learning for molecular property prediction. In WWW, pages 2559–2567, 2021.
  12. Inductive representation learning on large graphs. In NIPS, pages 1024–1034, 2017.
  13. Learning deep representations by mutual information estimation and maximization. In ICLR, 2019.
  14. Meta-learning in neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence, 2021.
  15. Strategies for pre-training graph neural networks. In ICLR, 2020.
  16. Edge-labeling graph neural network for few-shot learning. In CVPR, pages 11–20, 2019.
  17. Siamese neural networks for one-shot image recognition. In ICML deep learning workshop, page 0, 2015.
  18. The SIDER database of drugs and side effects. Nucleic Acids Res., pages 1075–1079, 2016.
  19. Learning to propagate labels: Transductive propagation network for few-shot learning. In ICLR, 2019.
  20. Adaptive task sampling for meta-learning. In ECCV, pages 752–769, 2020.
  21. Pytorch: An imperative style, high-performance deep learning library. In NeurIPS, pages 8024–8035, 2019.
  22. Toxcast chemical landscape: paving the road to 21st century toxicology. Chemical research in toxicology, pages 1225–1251, 2016.
  23. Similarity maps-a visualization strategy for molecular fingerprints and machine-learning methods. Journal of cheminformatics, pages 1–7, 2013.
  24. Maximum unbiased validation (muv) data sets for virtual screening based on pubchem bioactivity data. Journal of chemical information and modeling, pages 169–184, 2009.
  25. Computational methods in drug discovery. Pharmacological reviews, pages 334–395, 2014.
  26. Prototypical networks for few-shot learning. In NIPS, pages 4077–4087, 2017.
  27. Communicative representation learning on attributed molecular graphs. In IJCAI, pages 2831–2838, 2020.
  28. Matching networks for one shot learning. In NIPS, pages 3630–3638, 2016.
  29. Pubchem’s bioassay database. Nucleic acids research, pages D400–D412, 2012.
  30. Generalizing from a few examples: A survey on few-shot learning. ACM Comput. Surv., pages 63:1–63:34, 2020.
  31. Property-aware relation networks for few-shot molecular property prediction. In NeurIPS, pages 17441–17454, 2021.
  32. Ronald J Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, pages 229–256, 1992.
  33. Moleculenet: a benchmark for molecular machine learning. Chemical science, pages 513–530, 2018.
  34. How powerful are graph neural networks? In ICLR, 2019.
  35. Meta-learning with an adaptive task scheduler. In NeurIPS, pages 7497–7509, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Xiang Zhuang (10 papers)
  2. Qiang Zhang (466 papers)
  3. Bin Wu (202 papers)
  4. Keyan Ding (18 papers)
  5. Yin Fang (32 papers)
  6. Huajun Chen (198 papers)
Citations (8)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now